© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200439
    Prev
    Next
    INDEX
    Explanations

    пи

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Drinks
    0.41
     వ‌
    0.40
    rupa
    0.38
     drinks
    0.38
    蜗
    0.37
    蓍
    0.37
    Pov
    0.37
     wr
    0.36
     во
    0.36
    drinks
    0.36
    POSITIVE LOGITS
     пи
    1.72
     Pis
    1.61
     pis
    1.60
    ピ
    1.55
     Пи
    1.50
     ピ
    1.48
    Pis
    1.45
     피
    1.44
    pis
    1.39
    Пи
    1.30
    Activations Density 0.002%

    No Known Activations